Another Trump Rape Surfaces

[Koyaanisqatsi]

It's not that it's the only conclusion you can draw from the data

Yes, it is.

but rather that there's no useful conclusion you can draw about how many were raped.

One can draw exactly two “useful” conclusions from the data: 1) that at least 1 out of every 2 women in America have been sexually assaulted at least once. 2) that the total number is likely higher.

All it sets is an upper bound.

Wrong again. Here is the question one last time: Have you, a close friend OR a family member ever been the victim of sexual assault?

That means no matter whether it was just you or it was you And a member of your family And a friend or friends, at least one incident of sexual assault will be counted.

So if anything it sets a lower bound, not an upper.

I strongly suspect this is from some piece-of-shit "research" designed to deceive those who read about it in the popular press.

It was a YouGov Poll, a screenshot of which I posted and you saw, reposted and responded to. Here it is again made idiot-proof:

 

[Loren Pechtel]

One can draw exactly two “useful” conclusions from the data: 1) that at least 1 out of every 2 women in America have been sexually assaulted at least once. 2) that the total number is likely higher.

Apparently you do not know what the word "or" means. Look at your "evidence" once again and see what it actually says.

 

[Koyaanisqatsi]

One can draw exactly two “useful” conclusions from the data: 1) that at least 1 out of every 2 women in America have been sexually assaulted at least once. 2) that the total number is likely higher.

Apparently you do not know what the word "or" means.

Irony. Big fan.

Look at your "evidence" once again and see what it actually says.

It says exactly what I just pointed out. Have you, a close friend or a family member been a victim of sexual assault?

If you, answer "yes."

If a family member, answer "yes."

If a friend, answer "yes."

If you and a family member, answer "yes."

If you and a friend, answer "yes."

If you and a family member and a friend, answer "yes."

If you and ten of your family members and thrity of your friends, answer "yes."

Etc.

THEREFORE, all "yes" answers are affirming at least one incidence of sexaul assault.

THEREFORE, the total of 50% reflects the fact that at least 1 out of every 2 women in America have been the victim of a sexual assault.

Which further means that the actual number is likely much higher precisely because that is the lower bound, not the upper.

 

[Loren Pechtel]

Irony. Big fan.

Look at your "evidence" once again and see what it actually says.

It says exactly what I just pointed out. Have you, a close friend or a family member been a victim of sexual assault?

If you, answer "yes."

If a family member, answer "yes."

If a friend, answer "yes."

If you and a family member, answer "yes."

If you and a friend, answer "yes."

If you and a family member and a friend, answer "yes."

If you and ten of your family members and thrity of your friends, answer "yes."

Etc.

THEREFORE, all "yes" answers are affirming at least one incidence of sexaul assault.

THEREFORE, the total of 50% reflects the fact that at least 1 out of every 2 women in America have been the victim of a sexual assault.

Which further means that the actual number is likely much higher precisely because that is the lower bound, not the upper.

You're doing your logic upside-down. Yes, every yes answer indicates an incidence of sexual assault. However, nothing in your data says how many people will answer yes for one incidence of sexual assault.

 

[Koyaanisqatsi]

Yes, every yes answer indicates an incidence of sexual assault.

Then we can extrapolate that AT LEAST 50% of women have been sexually assaulted as a lower bound.

 

[Loren Pechtel]

Yes, every yes answer indicates an incidence of sexual assault.

Then we can extrapolate that AT LEAST 50% of women have been sexually assaulted as a lower bound.

No.

We have group A. 100 women, one was raped. They talk about such things, 20 of the women know that one was raped. Your survey gets 21%.

Group B, however, doesn't talk about such things. We get 1% from the survey.

 

[Koyaanisqatsi]

Yes, every yes answer indicates an incidence of sexual assault.

Then we can extrapolate that AT LEAST 50% of women have been sexually assaulted as a lower bound.

No.

Yes.

We have group A.

Wrong. We have a POLL and a pool of respondents that will then be representative of the nation as a whole.

They don't know each other. They have never met each other. They are not in a room somewhere all talking to one another. They are in their homes and asked to answer several different questions.

One of the poll questions is: Have you, a close friend or a family member been sexually assaulted?

If any female (or male, we haven't even addressed them), respondent answers, "yes" then that means AT LEAST ONE instance of sexual assault.

THEREFORE, extrapolating the total of 50% of the women surveyed responding "yes" to that question reflects the fact that AT LEAST ONE OUT OF TWO women in America have been the victim of a sexual assault.

Which further means that the actual number is likely much higher precisely because that is the lower bound, not the upper.

This is incontrovertible. This is how a poll works. It is not possible that you can't understand that.

 

[Loren Pechtel]

No.

Yes.

We have group A.

Wrong. We have a POLL and a pool of respondents that will then be representative of the nation as a whole.

They don't know each other. They have never met each other. They are not in a room somewhere all talking to one another. They are in their homes and asked to answer several different questions.

One of the poll questions is: Have you, a close friend or a family member been sexually assaulted?

If any female (or male, we haven't even addressed them), respondent answers, "yes" then that means AT LEAST ONE instance of sexual assault.

THEREFORE, extrapolating the total of 50% of the women surveyed responding "yes" to that question reflects the fact that AT LEAST ONE OUT OF TWO women in America have been the victim of a sexual assault.

Which further means that the actual number is likely much higher precisely because that is the lower bound, not the upper.

This is incontrovertible. This is how a poll works. It is not possible that you can't understand that.

You're not making any sense here.

The question was whether you or someone you know were a victim. 50% saying yes means 50% either were assaulted or knew someone who was assaulted. You have no data to decide which bin they are in, yet you are assuming they were all in the first bin.

 

[Koyaanisqatsi]

Wrong. We have a POLL and a pool of respondents that will then be representative of the nation as a whole.

They don't know each other. They have never met each other. They are not in a room somewhere all talking to one another. They are in their homes and asked to answer several different questions.

One of the poll questions is: Have you, a close friend or a family member been sexually assaulted?

If any female (or male, we haven't even addressed them), respondent answers, "yes" then that means AT LEAST ONE instance of sexual assault.

THEREFORE, extrapolating the total of 50% of the women surveyed responding "yes" to that question reflects the fact that AT LEAST ONE OUT OF TWO women in America have been the victim of a sexual assault.

Which further means that the actual number is likely much higher precisely because that is the lower bound, not the upper.

This is incontrovertible. This is how a poll works. It is not possible that you can't understand that.

You're not making any sense here.

The question was whether you or someone you know were a victim.

The question was (verbatim): Have you, a close friend or family member ever been a victim of sexual assault?

If you, then answer "yes."
If a close friend, then answer "yes."
If a family member, then answer "yes."
If you AND a family member AND a close friend, then answer "yes."
If not you, and not a family member, and not a close friend, then answer "no."

50% answered "yes," which means that AT LEAST half of all women (likely more) have been sexually assaulted.

That is how you extrapolate the findings.

50% saying yes means 50% either were assaulted or knew someone who was assaulted.

Right, so AT LEAST HALF have been sexually assaulted. How is possible you still can't get that?

You have no data to decide which bin they are in

The "bin" they are in is the YES bin, which counts as: at least one instance of a sexual assault. Maybe more (probably more), but at least one instance.

50% is the lower bound, not the upper precisely because there could be a respondent who was, (a) sexually assaulted; (b) has a family member that was sexually assaulted; (c) has a close friend that was sexually assaulted; (d) has several close friends that were sexually assaulted; (e), knows twenty other people throughout her life who were sexually assaulted. Or it could just be one instance.

So, it's possible that some twenty five instances would still only count as one instance in regard to the poll, but ALL instances count for at least one instance.

Which, once again, when extrapolated means at least HALF of all women have been sexually assaulted.

 

[Jimmy Higgins]

Are you guys still going back and forth on this?

 

[Gun Nut]

oh oh oh... let me play too!

Not only all that back and fourth... but some number of respondents that said "yes" were referring to the same victim. A family of 5 may all have said yes that they are aware that one family member was a victim. That's 5 yeses for 1 incident.

 

[Elixir]

Trump is a rapist.

 

[Loren Pechtel]

That's how I feel about you continuing to get the math backwards.

50% answered "yes," which means that AT LEAST half of all women (likely more) have been sexually assaulted.

That is how you extrapolate the findings.

Except you're doing it backwards. It's at most, not at least.

50% saying yes means 50% either were assaulted or knew someone who was assaulted.

Right, so AT LEAST HALF have been sexually assaulted. How is possible you still can't get that?

You have two families, each containing 5 women. One is raped, she tells her family.

50% answer the question yes, 10% were raped.

You have no data to decide which bin they are in

The "bin" they are in is the YES bin, which counts as: at least one instance of a sexual assault. Maybe more (probably more), but at least one instance.

50% is the lower bound, not the upper precisely because there could be a respondent who was, (a) sexually assaulted; (b) has a family member that was sexually assaulted; (c) has a close friend that was sexually assaulted; (d) has several close friends that were sexually assaulted; (e), knows twenty other people throughout her life who were sexually assaulted. Or it could just be one instance.

So, it's possible that some twenty five instances would still only count as one instance in regard to the poll, but ALL instances count for at least one instance.

Which, once again, when extrapolated means at least HALF of all women have been sexually assaulted.

While there will be a few who could answer the question yes for more than one reason they're a minority--and that still doesn't address the women who only knew someone but weren't attacked.

 

[Koyaanisqatsi]

You have two families, each containing 5 women.

Nooooo, you have 100 representative women (or however many were in the respondent pool), who don't know one another and live in completely different states from one another, all answering the same question for a poll. The question is: Have you, a family member or a close friend ever been the victim of sexual assault?

50 of those women--who do not know each other and are not family members with each other--answer "yes."

Which, once again, when extrapolated means, at least HALF of all women have been sexually assaulted.

That's how a poll works.

 

[Loren Pechtel]

You have two families, each containing 5 women.

Nooooo, you have 100 representative women (or however many were in the respondent pool), who don't know one another and live in completely different states from one another, all answering the same question for a poll. The question is: Have you, a family member or a close friend ever been the victim of sexual assault?

50 of those women--who do not know each other and are not family members with each other--answer "yes."

Which, once again, when extrapolated means, at least HALF of all women have been sexually assaulted.

That's how a poll works.

I set up a scenario in which 50% say yes but only 10% were raped. Thus it's possible to have only 10% with the survey question.

Spreading it out doesn't really change things, you're asking different women but the pattern remains. If each woman tells 4 then you're at about 10% actually raped.

 

[Koyaanisqatsi]

You have two families, each containing 5 women.

Nooooo, you have 100 representative women (or however many were in the respondent pool), who don't know one another and live in completely different states from one another, all answering the same question for a poll. The question is: Have you, a family member or a close friend ever been the victim of sexual assault?

50 of those women--who do not know each other and are not family members with each other--answer "yes."

Which, once again, when extrapolated means, at least HALF of all women have been sexually assaulted.

That's how a poll works.

I set up a scenario in which 50% say yes but only 10% were raped.

You "set up a scenario"? Well look at you putting your big boy pants on.

Did the poll do that, though? Which is the only relevant question.

No, it did not. It did not ask the women in "two families, each containing 5 women" the question.

THIS poll--the professionally conducted poll, using a representative sample of people who don't know each other and aren't members of each other's families--extrapolates to at least half of all women in America having been sexually assaulted and that this number is the lower bound, which means it's likely much higher.

So, are you done yet, or is there more pointless derail up your ass?

 

[Loren Pechtel]

I set up a scenario in which 50% say yes but only 10% were raped.

You "set up a scenario"? Well look at you putting your big boy pants on.

Did the poll do that, though? Which is the only relevant question.

No, it did not. It did not ask the women in "two families, each containing 5 women" the question.

THIS poll--the professionally conducted poll, using a representative sample of people who don't know each other and aren't members of each other's families--extrapolates to at least half of all women in America having been sexually assaulted and that this number is the lower bound, which means it's likely much higher.

So, are you done yet, or is there more pointless derail up your ass?

I used a small group to get a 100% sample so there could be no statistical error. The whole point of polling is to use a representative sample to guess at the actual value. Scale it up and sample instead of asking everyone and you should get the same results with a bit of statistical error thrown in the mix. You have flunked basic statistics here.

 

[Koyaanisqatsi]

I set up a scenario in which 50% say yes but only 10% were raped.

You "set up a scenario"? Well look at you putting your big boy pants on.

Did the poll do that, though? Which is the only relevant question.

No, it did not. It did not ask the women in "two families, each containing 5 women" the question.

THIS poll--the professionally conducted poll, using a representative sample of people who don't know each other and aren't members of each other's families--extrapolates to at least half of all women in America having been sexually assaulted and that this number is the lower bound, which means it's likely much higher.

So, are you done yet, or is there more pointless derail up your ass?

I used a small group to get a 100% sample so there could be no statistical error.

Horseshit. You rigged your "poll" to achieve a preconceived outcome. You flunked life.

 

[ideologyhunter]

Don't you mean, 'YOU'RE FIRED!!!!'?

 

[Loren Pechtel]

I used a small group to get a 100% sample so there could be no statistical error.

Horseshit. You rigged your "poll" to achieve a preconceived outcome. You flunked life.

It's not possible to have rigged it as I was simply illustrating.

How does the set of data I provided not fit the poll?